检索结果-内蒙古大学图书馆

Imitation guided learning in learning classifier systems

Natural Computing 2009年第1期8卷 29-56页

作者： Métivier, Marc Lattaud, Claude LIAP5-UFR de Mathématiques et d'Informatique Centre Universitaire des Saints-Pères Université René Descartes (Paris 5) Paris 75006 45 rue des Saints-Pères France

In this paper, we study the means of developing an imitation process allowing to improve learning in the framework of learning classifier systems. We present three different approaches in the way a behavior observed may be taken into account through a guidance interaction: two approaches using a model of this behavior, and one without modelling. Those approaches are evaluated and compared in different environments when they are applied to three major classifier systems: ZCS, XCS and ACS. Results are analyzed and discussed. They highlight the importance of using a model of the observed behavior to enable an efficient imitation. Moreover, they show the advantages of taking this model into account by a specialized internal action. Finally, they bring new results of comparison between ZCS, XCS and ACS. © Springer Science+Business Media B.V. 2007.

关键词： ACS Imitation learning classifier system XCS ZCS

来源：评论

学校读者我要写书评

暂无评论

How Should learning classifier systems Cover A State-Action Space?

How Should Learning Classifier Systems Cover A State-Action ...

引用

IEEE Congress on Evolutionary Computation (CEC)

作者： Nakata, Masaya Lanzi, Pier Luca Kovacs, Tim Browne, Will Neil Takadama, Keiki Univ Electrocommun Tokyo Japan Politecn Milan Milan Italy Univ Bristol Bristol Avon England Victoria Univ Wellington Wellington New Zealand

ISBN: (纸本)9781479974924

A learning strategy in learning classifier systems (LCSs) defines how classifiers cover a state-action space in a problem. Previous analyses in classification problems have empirically claimed an adequate learning strategy can be decided depending on the types of noise in the problem. This issue is still arguable from two aspects. First, there lacks comparison of learning strategies in reinforcement learning problems with different types of noise. Second, when we can claim so, a further issue is how should classifiers cover the state-action space in order to improve the stability of LCS performance on as many types of noise as possible? This paper first attempts to empirically conclude these issues on a version of LCSs (i.e., the XCS classifier system). That is, we present a new concept of learning strategy for LCSs, and complement that claim by comparing it with the existing learning strategies on a reinforcement learning problem. Our learning strategy covers all state-action pairs but assigns more classifiers to the highest-return action at each state than other actions. Our results support that claim that existing learning strategies have dependencies on the types of noise in reinforcement learning problems. However, our learning strategy improves the stability of XCS performance compared with the existing strategies on all types of noise employed in this paper.

关键词： learning classifier system XCS complete action map best action map reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

User-centred Design and Development of a Graphical User Interface for learning classifier systems

User-centred Design and Development of a Graphical User Inte...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Babu, Sooraj K. Schneider, Tim von Mammen, Sebastian Julius Maximilians Univ Games Engn Wurzburg Germany

ISBN: (纸本)9798400701207

This study presents an application that offers an interactive representation of the learning cycle of a learning classifier system (LCS), a rule-based machine learning technique. The research approach utilized a combination of human-computer interaction requirements, design heuristics, and user-centred engineering to scaffold the development of a graphical user interface for an LCS. The evaluation of the application by LCS experts and a novice yielded encouraging results, demonstrating its ability to convey the LCS mechanics to the users. In addition, the experts validated the correctness of the learning cycle. The study's contribution is two-fold: it presents an innovative approach to making the user understand the underlying mechanics of LCS and validates the effectiveness of the developed application. Furthermore, this work sets the stage for future research towards design revision and to further develop the application to accommodate different LCS models and custom data.

关键词： learning classifier system Decision Making Learnability GUI

来源：评论

学校读者我要写书评

暂无评论

A comparison of Rule Compaction Algorithms for Michigan Style learning classifier systems 22

A comparison of Rule Compaction Algorithms for Michigan Styl...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Liu, Yi Browne, Will N. Xue, Bing Victoria Univ Wellington Wellington New Zealand Queensland Univ Technol Brisbane Qld 4001 Australia

ISBN: (纸本)9781450392686

learning classifier systems (LCSs) excel in data mining tasks, e.g. an LCS optimal model contains patterns that can precisely reveal how features identify classes for the explored problem. EC is stochastic, which leads to LCSs producing and keeping redundant rules that obscure the patterns. Thus, LCSs employ rule compaction methods to improve models by removing problematic rules. However, former compaction methods often fail to highlight the patterns and reduce accuracy after compaction. A survey of compaction methods is provided to investigate why compaction algorithms are incompetent in achieving expected performance. This work discovers a new LCS's optimal solution format, which refers to a model consisting of all correct unsubsumable rules in a given search space. This optimal solution is accurate in arbitrary noiseless datasets and contains interpretable patterns naturally. Thus, two compaction methods, specifying the production of such optimal solutions, are proposed. Successful compaction is demonstrated on complex and real problems with noiseless datasets, e.g. the 11-bits Majority-On problem that requires 924 different interacting rules in the optimum solution to be uniquely identified to enable correct visualization of the discovered knowledge. For the first time, the patterns contained in learned models for the large-scale 70-bits Multiplexer problem are visualized successfully.

关键词： learning classifier system rule compaction algorithm

来源：评论

学校读者我要写书评

暂无评论

Absumption to Complement Subsumption in learning classifier systems

Absumption to Complement Subsumption in Learning Classifier ...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Liu, Yi Browne, Will N. Xue, Bing Victoria Univ Wellington Sch Engn & Comp Sci Wellington New Zealand

ISBN: (纸本)9781450361118

learning classifier systems (LCSs), a 40-year-old technique, evolve interrogatable production rules. XCSs are the most popular reinforcement learning based LCSs. It is well established that the subsumption method in XCSs removes overly detailed rules. However, the technique still suffers from overly general rules that reduce accuracy and clarity in the discovered patterns. This adverse impact is especially true for domains that are containing accurate solutions that overlap, i.e. one data instance is covered by two plausible, but competing rules. A novel method, termed absumption, is introduced to counter over-general rules. Complex Boolean problems that contain epistasis, heterogeneity and overlap are used to test the absumption method. Results show that absumption successfully improves the training performance of XCSs by counteracting over-general rules. Moreover, absumption enables the rule-set to be compacted, such that underlying patterns can be precisely visualized successfully. Additionally, the equations for the optimal size of solutions for a problem domain can now be determined.

关键词： learning classifier system Absumption Subsumption

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of Action Map in learning classifier systems

引用

SICE Journal of Control, Measurement, and system Integration 2018年第3期11卷 239-248页

作者： Masaya Nakata Keiki Takadama Graduate School of Engineering Yokohama National University Graduate School of Informatics The University of Electro-Communications

An action map is one of the most fundamental options in designing a learning classifier system (LCS), which defines how LCSs cover a state action space in a problem. It still remains unclear which action map can be adequate to solve which type of problem effectively, resulting in a lack of basic design methodology of LCS in terms of the action map. This paper attempts to empirically conclude this issue with an intensive analysis comparing different action maps on LCSs. From the analysis on a benchmark classification problem, we identify a fact that an adequate action map can be determined depending on a type of problem difficulty such as class imbalance, more generally, a complexity of classification or decision boundary of problem. We also conduct an experiment on a human activity recognition task as a real world classification problem, and then confirm that a suggested adequate action map from the analysis enables an LCS to improve on the performance. Those results claim that the action map should be selected adequately in designing LCSs in order to improve their potential performance.

关键词： learning classifier system action map performance analysis evolutionary computation classification

来源：评论

学校读者我要写书评

暂无评论

Context-aware mobile service adaptation via a Co-evolution eXtended classifier system in mobile network environments

引用

MOBILE INFORMATION systemS 2014年第2期10卷 197-215页

作者： Wang, Shangguang Zheng, Zibin Wu, Zhengping Sun, Qibo Zou, Hua Yang, Fangchun Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100088 Peoples R China Chinese Univ Hong Kong Shenzhen Res Inst Hong Kong Hong Kong Peoples R China Univ Bridgeport Dept Comp Sci & Engn Bridgeport CT USA

With the popularity of mobile services, an effective context-aware mobile service adaptation is becoming more and more important for operators. In this paper, we propose a Co-evolution eXtended classifier system (CXCS) to perform context-aware mobile service adaptation. Our key idea is to learn user context, match adaptation rule, and provide the best suitable mobile services for users. Different from previous adaptation schemes, our proposed CXCS can produce a new user's initial classifier population to quicken its converging speed. Moreover, it can make the current user to predict which service should be selected, corresponding to an uncovered context. We compare CXCS based on a common mobile service adaptation scenario with other five adaptation schemes. The results show the adaptation accuracy of CXCS is higher than 70% on average, and outperforms other schemes.

关键词： Mobile service context-aware service adaptation learning classifier system eXtended classifier system Co-evolution

来源：评论

学校读者我要写书评

暂无评论

Mining knowledge from data using anticipatory classifier system

引用

KNOWLEDGE-BASED systemS 2008年第5期21卷 363-370页

作者： Unold, Olgierd Tuszynski, Krzysztof Wroclaw Univ Technol Inst Comp Engn Control & Robot PL-50370 Wroclaw Poland

The article demonstrates the capabilities of Anticipatory classifier system in solving the data mining tasks. It is a first application of anticipatory learning to a real world exploration tasks. The results of experiments with Monk's, Voting-record and WBC problems are shown as well as comparison of these results with other systems is presented. ACS handles these tasks quite well even though it is designed for a different kind of problems. (c) 2008 Elsevier B.V. All rights reserved.

关键词： learning classifier system data mining knowledge representation anticipatory classifier system

来源：评论

学校读者我要写书评

暂无评论

Integrating extended classifier system and knowledge extraction model for financial investment prediction: An empirical study

引用

EXPERT systemS WITH APPLICATIONS 2006年第1期31卷 174-183页

作者： Chen, AP Chen, MY Natl Chiao Tung Univ Inst Informat Management Hsinchu 30050 Taiwan

Machine learning methods such as fuzzy logic, neural networks and decision tree induction have been applied to learn rules, however they can get trapped into a local optimal. Based on the principle of natural evolution and global searching, a genetic algorithm is promising for obtaining better results. This article adopts the learning classifier systems (LCS) technique to provide a three-phase knowledge extraction methodology, which makes continues and instant learning while integrates multple rule sets into a centralized knowledge base. This paper makes three important contributions: (1) it represents various rule sets that are derived from different sources and encoded as a fixed-length bit string in the knowledge encoding phase;(2) it uses three criteria (accuracy, coverage, and fitness) to select an optimal set of rules from a large population in the knowledge extraction phase;(3) it applies genetic operations to generate optimal rule sets in the knowledge integration phase. The experiments prove that the rule sets derived by the proposed approach is more accurate than other machine learning algorithm. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： learning classifier system extended classifier system knowledge extraction machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive support framework for wisdom web of things

引用

WORLD WIDE WEB-INTERNET AND WEB INFORMATION systemS 2013年第4期16卷 379-398页

作者： Gao, Yang Lin, Mufeng Wang, Ruili Nanjing Univ State Key Lab Novel Software Technol Nanjing 210008 Jiangsu Peoples R China Massey Univ Sch Engn & Adv Technol Palmerston North New Zealand

Wisdom Web of Things (W2T) is the next generation of networks, which provides ubiquitous wisdom services in a ubiquitous network in the hyper world. Adaptiveness is the key issue of realizing the harmonious unity of human-information-thing. This paper proposes a self-adaptive support framework for W2T, which has three important components: (i) An adaptive requirement description language, which is to describe the wisdom service models and self-adaptive wisdom service strategies. (ii) Forward reasoning and backward planning ability. We propose that forward reasoning can be implemented based on the Rete algorithm and backward planning can be implemented based on a Hierarchical Task Network (HTN), which enable W2T to achieve complex, rapid, and efficient reasoning and planning to provide active, transparent, safe, and reliable services. (iii) A knowledge base evolution mechanism based on a learning classifier system, which is to realize the evolution of the knowledge base, and to satisfy the dynamic requirements of wisdom services. We take a wisdom traffic system as an example to demonstrate the data conversion mechanism and the functions of the proposed self-adaptive support framework.

关键词： wisdom web of things adaptive suppport framework adaptive requirement description language Rete hierarchical task network learning classifier system

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：